Qwen3.5-122B-A10B-abliterix · mradermacher

Qwen3.5-122B-A10B-abliterix I1-IQ3_S

This file is exactly 52,924,024,512 bytes — 49.29 GiB / 52.92 GB at an effective 3.467 bits per weight. The nominal rate for I1-IQ3_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

49.29 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Qwen3.5-122B-A10B-abliterated-v1-i1-GGUF:I1-IQ3_S

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download mradermacher/Qwen3.5-122B-A10B-abliterated-v1-i1-GGUF Qwen3.5-122B-A10B-abliterated-v1.i1-IQ3_S.gguf
Direct download

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.

Repository →
Size
49.29 GiB
52.92 GB
Effective bpw
3.467
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata